© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 154818
    Prev
    Next
    INDEX
    Explanations

    growth, square, development, census

    np_acts-logits-general · gemini-2.5-flash-lite

    journaling or writing about dreams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ext
    0.46
     damped
    0.45
     exclusivement
    0.42
    ノ
    0.42
     ward
    0.41
    Ward
    0.41
    다
    0.41
    ellia
    0.41
    く
    0.41
     නි
    0.40
    POSITIVE LOGITS
    ')(
    0.51
    ouncement
    0.45
    栘
    0.45
    arrayList
    0.45
    綎
    0.44
     floribus
    0.44
    ⺌
    0.44
    琭
    0.44
    ’).
    0.43
     Raton
    0.43
    Activations Density 0.001%

    No Known Activations